def test_training_script(tmpdir):
train_dialogue_model(DEFAULT_DOMAIN_PATH, DEFAULT_STORIES_FILE,
tmpdir.strpath,
policy_config='data/test_config/max_hist_config.yml',
interpreter=RegexInterpreter(),
kwargs={})
assert True
def test_remote_example():
from rasa_core import train, run
train.train_dialogue_model("examples/remotebot/concert_domain_remote.yml",
"examples/remotebot/data/stories.md",
"examples/remotebot/models/dialogue", False,
None, {})
agent = run.main("examples/remotebot/models/dialogue")
response = agent.start_message_handling("_search_venues")
assert response.get("next_action") == 'search_venues'
assert response.get("tracker") == {
'slots': {
'concerts': None,
'venues': None
},
'sender_id': 'default',
'paused': False,
'latest_message': {
'text': '_search_venues',
'intent_ranking': [{
'confidence': 1.0,
'name': 'search_venues'
}],
'intent': {
'confidence': 1.0,
'name': 'search_venues'
},
'entities': []
}
}
next_response = agent.continue_message_handling("default", "search_venues",
[])
assert next_response.get("next_action") == "action_listen"
def test_training_script(tmpdir):
train_dialogue_model(DEFAULT_DOMAIN_PATH, DEFAULT_STORIES_FILE,
tmpdir.strpath,
use_online_learning=False,
nlu_model_path=None,
kwargs={})
assert True
def test_training_script(tmpdir):
train_dialogue_model(DEFAULT_DOMAIN_PATH,
DEFAULT_STORIES_FILE,
tmpdir.strpath,
interpreter=RegexInterpreter(),
kwargs={})
assert True
def test_training_script_with_restart_stories(tmpdir):
train_dialogue_model(DEFAULT_DOMAIN_PATH,
"data/test_stories/stories_restart.md",
tmpdir.strpath,
interpreter=RegexInterpreter(),
kwargs={})
assert True
def test_training_script(tmpdir):
train_dialogue_model(DEFAULT_DOMAIN_PATH,
DEFAULT_STORIES_FILE,
tmpdir.strpath,
use_online_learning=False,
nlu_model_path=None,
kwargs={})
def trained_moodbot_path():
train.train_dialogue_model(domain_file="examples/moodbot/domain.yml",
stories_file="examples/moodbot/data/stories.md",
output_path=MOODBOT_MODEL_PATH,
interpreter=RegexInterpreter(),
max_history=None,
kwargs=None)
return MOODBOT_MODEL_PATH
def trained_moodbot_path():
train.train_dialogue_model(domain_file="examples/moodbot/domain.yml",
stories_file="examples/moodbot/data/stories.md",
output_path=MOODBOT_MODEL_PATH,
interpreter=RegexInterpreter(),
policy_config='rasa_core/default_config.yml',
kwargs=None)
return MOODBOT_MODEL_PATH
def test_remote_training(tmpdir):
train_dialogue_model("examples/remote/concert_domain_remote.yml",
"examples/remote/data/stories.md",
tmpdir.strpath, {})
agent = Agent.load(tmpdir.strpath)
assert agent.domain._factory_name == "remote"
action_types = [type(a) for a in agent.domain.actions]
assert action_types[:3] == [ActionListen, ActionRestart, RemoteAction]
def test_training_script_with_max_history_set(tmpdir):
max_history = 3
train_dialogue_model(DEFAULT_DOMAIN_PATH, DEFAULT_STORIES_FILE,
tmpdir.strpath,
nlu_model_path=None,
max_history=max_history,
kwargs={})
agent = Agent.load(tmpdir.strpath)
for policy in agent.policy_ensemble.policies:
if hasattr(policy.featurizer, 'max_history'):
assert policy.featurizer.max_history == max_history
def test_training_script_without_max_history_set(tmpdir):
train_dialogue_model(DEFAULT_DOMAIN_PATH, DEFAULT_STORIES_FILE,
tmpdir.strpath,
interpreter=RegexInterpreter(),
max_history=None,
kwargs={})
agent = Agent.load(tmpdir.strpath)
for policy in agent.policy_ensemble.policies:
if hasattr(policy.featurizer, 'max_history'):
assert policy.featurizer.max_history == \
policy.featurizer.MAX_HISTORY_DEFAULT
def train_dialogue(domain_file="config/domain.yml",
model_path="models/dialogue",
stories_file="config/stories.md",
policy_config="config/policy_config.yml"):
#endpoints_file="config/endpoints.yml"):
train_dialogue_model(domain_file=domain_file,
stories_file=stories_file,
output_path=model_path,
policy_config=policy_config,
kwargs=_additional_arguments())
def trained_moodbot_path():
model_path = "examples/moodbot/models/dialogue"
train.train_dialogue_model(
domain_file="examples/moodbot/domain.yml",
stories_file="examples/moodbot/data/stories.md",
output_path=model_path,
use_online_learning=False,
nlu_model_path=None,
max_history=None,
kwargs=None
)
return model_path
def trained_moodbot_path():
model_path = "examples/moodbot/models/dialogue"
train.train_dialogue_model(
domain_file="examples/moodbot/domain.yml",
stories_file="examples/moodbot/data/stories.md",
output_path=model_path,
use_online_learning=False,
nlu_model_path=None,
max_history=None,
kwargs=None
)
return model_path
def test_training_script_without_max_history_set(tmpdir):
train_dialogue_model(DEFAULT_DOMAIN_PATH, DEFAULT_STORIES_FILE,
tmpdir.strpath,
use_online_learning=False,
nlu_model_path=None,
max_history=None,
kwargs={})
agent = Agent.load(tmpdir.strpath)
for policy in agent.policy_ensemble.policies:
if hasattr(policy.featurizer, 'max_history'):
assert policy.featurizer.max_history == \
policy.featurizer.MAX_HISTORY_DEFAULT
def test_training_script_with_max_history_set(tmpdir):
train_dialogue_model(DEFAULT_DOMAIN_PATH, DEFAULT_STORIES_FILE,
tmpdir.strpath,
interpreter=RegexInterpreter(),
policy_config='data/test_config/max_hist_config.yml',
kwargs={})
agent = Agent.load(tmpdir.strpath)
for policy in agent.policy_ensemble.policies:
if hasattr(policy.featurizer, 'max_history'):
if type(policy) == FormPolicy:
assert policy.featurizer.max_history == 2
else:
assert policy.featurizer.max_history == 5
def test_remote_example():
from rasa_core import train, run
from rasa_core.events import SlotSet
train.train_dialogue_model(
domain_file="examples/remotebot/concert_domain_remote.yml",
stories_file="examples/remotebot/data/stories.md",
output_path="examples/remotebot/models/dialogue",
use_online_learning=False,
nlu_model_path=None,
max_history=None,
kwargs=None)
agent = run.main("examples/remotebot/models/dialogue")
response = agent.start_message_handling("/search_venues")
assert response.get("next_action") == 'search_venues'
reference = {
'slots': {
'concerts': None,
'venues': None
},
'events': None,
'sender_id': 'default',
'paused': False,
'latest_event_time': 1513023382.101372,
'latest_message': {
'text': '/search_venues',
'intent_ranking': [{
'confidence': 1.0,
'name': 'search_venues'
}],
'intent': {
'confidence': 1.0,
'name': 'search_venues'
},
'entities': []
}
}
result = response.get("tracker")
assert reference.keys() == result.keys()
del reference['latest_event_time']
del result['latest_event_time']
assert reference == result
venues = [{"name": "Big Arena", "reviews": 4.5}]
next_response = agent.continue_message_handling(
"default", "search_venues", [SlotSet("venues", venues)])
assert next_response.get("next_action") == "action_listen"
def test_remote_training(tmpdir):
train_dialogue_model("examples/remotebot/concert_domain_remote.yml",
"examples/remotebot/data/stories.md",
tmpdir.strpath,
use_online_learning=False,
nlu_model_path=None,
kwargs={})
agent = Agent.load(tmpdir.strpath)
assert agent.domain._factory_name == "remote"
action_types = [type(a) for a in agent.domain.actions]
assert action_types[:4] == [ActionListen, ActionRestart,
ActionDefaultFallback, RemoteAction]
def test_remote_training(tmpdir):
train_dialogue_model("examples/remotebot/concert_domain_remote.yml",
"examples/remotebot/data/stories.md",
tmpdir.strpath,
use_online_learning=False,
nlu_model_path=None,
kwargs={})
agent = Agent.load(tmpdir.strpath)
assert agent.domain._factory_name == "remote"
action_types = [type(a) for a in agent.domain.actions]
assert action_types[:4] == [
ActionListen, ActionRestart, ActionDefaultFallback, RemoteAction
]
def test_moodbot_example():
from rasa_core import train, run
train.train_dialogue_model("examples/moodbot/domain.yml",
"examples/moodbot/data/stories.md",
"examples/moodbot/models/dialogue", False, None,
{})
agent = run.main("examples/moodbot/models/dialogue")
responses = agent.handle_message("_greet")
assert responses[0] == 'Hey! How are you?'
responses.extend(agent.handle_message("_mood_unhappy"))
assert responses[-1] in {"Did that help you?"}
# (there is a 'I am on it' message in the middle we are not checking)
assert len(responses) == 6
def train_agent():
return train.train_dialogue_model(domain_file="domain.yml",
stories_file="data/stories.md",
output_path="models/dialogue",
kwargs={"batch_size": 50,
"epochs": 200,
"max_training_samples": 300
})
def train_dialogue(self,
domain_file='domain.yml',
stories_file='data/stories.md',
model_path='model/dialogue',
policy_config='config/config.yml'):
return train.train_dialogue_model(domain_file=domain_file,
stories_file=stories_file,
output_path=model_path,
policy_config=policy_config)
def train_dialogue(domain_file, model_path, training_folder, policy_config):
return train.train_dialogue_model(domain_file=domain_file,
stories_file=training_folder,
output_path=model_path,
policy_config=policy_config,
kwargs={
'augmentation_factor': 20,
'validation_split': 0.2,
})
def test_formbot_example():
sys.path.append("examples/formbot/")
p = "examples/formbot/"
stories = os.path.join(p, "data", "stories.md")
endpoint = EndpointConfig("https://abc.defg/webhooks/actions")
endpoints = AvailableEndpoints(action=endpoint)
agent = train_dialogue_model(os.path.join(p, "domain.yml"),
stories,
os.path.join(p, "models", "dialogue"),
endpoints=endpoints,
policy_config="rasa_core/default_config.yml")
response = {
'events': [{
'event': 'form',
'name': 'restaurant_form',
'timestamp': None
}, {
'event': 'slot',
'timestamp': None,
'name': 'requested_slot',
'value': 'cuisine'
}],
'responses': [{
'template': 'utter_ask_cuisine'
}]
}
httpretty.register_uri(httpretty.POST,
'https://abc.defg/webhooks/actions',
body=json.dumps(response))
httpretty.enable()
responses = agent.handle_text("/request_restaurant")
httpretty.disable()
assert responses[0]['text'] == 'what cuisine?'
response = {
"error": "Failed to validate slot cuisine with action restaurant_form",
"action_name": "restaurant_form"
}
httpretty.register_uri(httpretty.POST,
'https://abc.defg/webhooks/actions',
status=400,
body=json.dumps(response))
httpretty.enable()
responses = agent.handle_text("/chitchat")
httpretty.disable()
assert responses[0]['text'] == 'chitchat'
def train_agent():
return train.train_dialogue_model(domain_file="domain.yml",
stories_file="data/stories.md",
output_path="models/dialogue",
endpoints="endpoints.yml",
max_history=2,
kwargs={"batch_size": 50,
"epochs": 200,
"max_training_samples": 300
})
def train_agent(interpreter):
return train.train_dialogue_model(domain_file="horoscope_domain.yml",
stories_file="data/stories.md",
output_path="models/dialog",
nlu_model_path=interpreter,
endpoints="endpoints.yml",
max_history=2,
kwargs={"batch_size": 50,
"epochs": 200,
"max_training_samples": 300
})
def test_remote_example():
from rasa_core import train, run
from rasa_core.events import SlotSet
train.train_dialogue_model(
domain_file="examples/remotebot/concert_domain_remote.yml",
stories_file="examples/remotebot/data/stories.md",
output_path="examples/remotebot/models/dialogue",
use_online_learning=False,
nlu_model_path=None,
max_history=None,
kwargs=None
)
agent = run.main("examples/remotebot/models/dialogue")
response = agent.start_message_handling("/search_venues")
assert response.get("next_action") == 'search_venues'
reference = {
'slots': {'concerts': None, 'venues': None},
'events': None,
'sender_id': 'default',
'paused': False,
'latest_event_time': 1513023382.101372,
'latest_message': {
'text': '/search_venues',
'intent_ranking': [{'confidence': 1.0, 'name': 'search_venues'}],
'intent': {'confidence': 1.0, 'name': 'search_venues'},
'entities': []}}
result = response.get("tracker")
assert reference.keys() == result.keys()
del reference['latest_event_time']
del result['latest_event_time']
assert reference == result
venues = [{"name": "Big Arena", "reviews": 4.5}]
next_response = agent.continue_message_handling(
"default", "search_venues", [SlotSet("venues", venues)]
)
assert next_response.get("next_action") == "action_listen"
def train_dialogue(domain_file='domain.yml',
stories_file='data/stories.md',
model_path='models/dialogue',
policy_config='policy_config.yml'):
return train.train_dialogue_model(domain_file=domain_file,
stories_file=stories_file,
output_path=model_path,
policy_config=policy_config,
kwargs={
'augmentation_factor': 50,
'validation_split': 0.2
})
def run_online(domain_file="config/domain.yml", stories_file="config/stories.md", output_path="models/dialogue",
max_history=3, kwargs={"batch_size": 50, "epochs": 800, "max_training_samples": 300}):
interpreter = RasaNLUInterpreter("models/ticket/nlu_bot")
agent = train.train_dialogue_model(domain_file=domain_file,
interpreter=interpreter,
stories_file=stories_file,
output_path=output_path,
max_history=max_history,
endpoints=AvailableEndpoints.read_endpoints("config/endpoints.yml"),
kwargs=kwargs)
online.run_online_learning(agent)
def test_random_seed(tmpdir, config_file):
# set random seed in config file to
# generate a reproducible training result
agent_1 = train_dialogue_model(DEFAULT_DOMAIN_PATH,
DEFAULT_STORIES_FILE,
tmpdir.strpath + "1",
interpreter=RegexInterpreter(),
policy_config=config_file,
kwargs={})
agent_2 = train_dialogue_model(DEFAULT_DOMAIN_PATH,
DEFAULT_STORIES_FILE,
tmpdir.strpath + "2",
interpreter=RegexInterpreter(),
policy_config=config_file,
kwargs={})
processor_1 = agent_1.create_processor()
processor_2 = agent_2.create_processor()
probs_1 = processor_1.predict_next("1")
probs_2 = processor_2.predict_next("2")
assert probs_1["confidence"] == probs_2["confidence"]
def test_formbot_example():
sys.path.append("examples/formbot/")
p = "examples/formbot/"
stories = os.path.join(p, "data", "stories.md")
endpoint = EndpointConfig("http://localhost:5055/webhook")
endpoints = AvailableEndpoints(action=endpoint)
agent = train_dialogue_model(os.path.join(p, "domain.yml"),
stories,
os.path.join(p, "models", "dialogue"),
endpoints=endpoints,
policy_config="rasa_core/default_config.yml")
# response = {
# 'events': [
# {'event': 'form', 'name': 'restaurant_form', 'timestamp': None},
# {'event': 'slot', 'timestamp': None,
# 'name': 'requested_slot', 'value': 'cuisine'}
# ],
# 'responses': [
# {'template': 'utter_ask_cuisine'}
# ]
# }
print(type(agent.policy_ensemble))
responses = agent.handle_text("/request_restaurant")
# assert responses[0]['text'] == 'what cuisine?'
print(responses)
# response = {
# "error": "Failed to validate slot cuisine with action restaurant_form",
# "action_name": "restaurant_form"
# }
responses = agent.handle_text("/chitchat")
# assert responses[0]['text'] == 'chitchat'
print(responses[0])
def test_training_script(tmpdir):
train_dialogue_model(DEFAULT_DOMAIN_PATH, DEFAULT_STORIES_FILE,
tmpdir.strpath, {})
def train_dialog():
conf = Config()
train_dialogue_model(conf.get_value('domain-file'), conf.get_value('stories-file'),
conf.get_value('dialog-model-path'))
def test_training_script(tmpdir):
train_dialogue_model(DEFAULT_DOMAIN_PATH, DEFAULT_STORIES_FILE,
tmpdir.strpath,
nlu_model_path=None,
kwargs={})
assert True
def trained_moodbot_path():
model_path = "examples/moodbot/models/dialogue"
train.train_dialogue_model("examples/moodbot/domain.yml",
"examples/moodbot/data/stories.md", model_path,
False, None, {})
return model_path
def train_dialog():
train_dialogue_model(CONF.get_value('domain-file'),
CONF.get_value('stories-file'),
CONF.get_value('dialog-model-path'))
